INDEX

Explanations

prepositions followed by a number or reference to a specific location

oai_token-act-pair · gpt-3.5-turbo Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res_fs24576-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.8.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

\/

-0.73

abet

-0.72

etus

-0.71

ãĥī

-0.69

CTV

-0.67

juven

-0.66

uman

-0.66

iculture

-0.60

ript

-0.60

auga

-0.60

POSITIVE LOGITS

 intermedi

0.85

shaw

0.78

 waivers

0.75

put

0.74

0.73

lace

0.72

out

0.72

lines

0.71

Activations Density 0.044%

prepositions followed by a number or reference to a specific location

No Comments

No Known Activations